A user has successfully jailbroken a PlayStation 5 console and managed to run the Qwen 27B large language model on its GPU. The model is reportedly achieving a speed of approximately 20 tokens per second. AI
IMPACT Demonstrates the potential for running LLMs on consumer gaming hardware, though performance is limited.
RANK_REASON This is a user-driven modification of existing hardware to run an AI model, not a product release from a major lab or a significant industry development.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →